© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11975
    Prev
    Next
    INDEX
    Explanations

    tested perfectly, same request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lke
    -0.27
    inski
    -0.22
    adel
    -0.21
    piel
    -0.21
    iten
    -0.21
    	iNdEx
    -0.21
    	RTLR
    -0.20
    çĽijåIJ¬é¡µéĿ¢
    -0.20
    	RTCT
    -0.20
    ÑĭÑĪ
    -0.19
    POSITIVE LOGITS
    åIJĮæł·çļĦ
    0.31
     identical
    0.26
    rames
    0.25
    åĭ¾
    0.25
    åľ¨åIJĮä¸Ģ
    0.24
    åĪ¥ãģ®
    0.24
     same
    0.24
    åIJĮ樣
    0.24
    åIJĮæł·
    0.24
    åIJĮãģĺ
    0.23
    Activations Density 0.503%

    No Known Activations